US 12,192,478 B2
Adaptively encoding video frames using content and network analysis
Yunbiao Lin, Shanghai (CN); Changliang Wang, Bellevue, WA (US); Ximin Zhang, San Jose, CA (US); Fan He, Shanghai (CN); Jill Boyce, Portland, OR (US); and Sri Ranjan Srikantam, Hillsboro, OR (US)
Assigned to INTEL CORPORATION, Santa Clara, CA (US)
Appl. No. 17/764,162
Filed by Intel Corporation, Santa Clara, CA (US)
PCT Filed Nov. 14, 2019, PCT No. PCT/CN2019/118301
§ 371(c)(1), (2) Date Mar. 25, 2022,
PCT Pub. No. WO2021/092821, PCT Pub. Date May 20, 2021.
Prior Publication US 2022/0408097 A1, Dec. 22, 2022
Int. Cl. H04N 19/146 (2014.01); H04N 19/142 (2014.01); H04N 19/172 (2014.01); H04N 19/184 (2014.01)
CPC H04N 19/146 (2014.11) [H04N 19/142 (2014.11); H04N 19/172 (2014.11); H04N 19/184 (2014.11)] 23 Claims
OG exemplary drawing
 
1. An apparatus for adaptively encoding video frames, comprising:
a network analyzer to predict an instant bitrate based on channel throughput feedback received from a network;
a content analyzer to generate ladder info based on a received frame;
an adaptive decision executer to:
after a determination that the ladder info is not empty, determine a frame rate, a video resolution, and a target frame size based on the predicted instant bitrate and the ladder outputs; and
after a determination that the ladder info is empty, determine the frame rate, the video resolution, and the target frame size based on a quantization parameter of a previously encoded frame and generated bits of the previously encoded frame; and
an encoder to encode the frame based on the frame rate, the video resolution, and the target frame size.